How to Use the CrowdSec MCP in OpenAI Agents SDK

Q: What's the best way to use the CrowdSec decision stream with the OpenAI Agents SDK?

Create a dedicated agent just for monitoring the getdecisionsstream. When it detects a new decision, it can use the SDK's handoff feature to pass the details to another, more specialized agent for remediation. This keeps your agent logic clean.

Give your OpenAI Agent production-ready threat intel from CrowdSec, with built-in safety checks before any action is taken.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrowdSec MCP to OpenAI Agents SDK

Create your Vinkius account to connect CrowdSec to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup CrowdSec with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check IP Reputations Instantly

Use `get_cti_smoke` to have your agent check any IP address against CrowdSec's global CTI database. It's a quick way to vet incoming connections or enrich security event data. The OpenAI Agent's guardrails can even prompt for confirmation before your agent acts on a high-risk IP. This works right out of the box. Since the OpenAI Agents SDK auto-discovers tools, your agent sees `get_cti_smoke` immediately after you connect the MCP Server. No extra mapping or configuration is needed.

Query Local Security Decisions

The `get_decisions` tool lets your agent query your own CrowdSec Local API (LAPI) for active decisions. You can build agents that automatically check if a user's IP is currently blocked before they attempt a sensitive action. It's direct access to your local security posture. The full trace history in the OpenAI dashboard shows you exactly which decisions your agent found and why it took the next step. This makes debugging security automation routines much simpler than digging through logs.

Stream Security Events to Your OpenAI Agent

Use the `get_decisions_stream` tool to give your agent a live feed of new and expiring security decisions from your CrowdSec instance. This turns your agent from a reactive tool into a proactive security monitor. It can watch for new blocks and trigger workflows in real-time. Because the OpenAI Agents SDK supports specialized agents, you can dedicate one agent to just monitoring this stream. When it sees a critical new decision, it can hand off the task to another agent built for incident response.

Setup guide

Set up CrowdSec MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CrowdSec tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CrowdSec tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CrowdSec tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CrowdSec Agent",
            instructions="You have access to CrowdSec tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by CrowdSec. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect CrowdSec now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about CrowdSec MCP in OpenAI Agents SDK

It's automatic. Just pass the MCP Server instance to the Agent constructor. The SDK handles tool discovery and validation, so your agent is ready to use the CrowdSec tools right away.

Yes. The OpenAI Agents SDK has built-in guardrails. You can configure it to require human confirmation before the agent takes a destructive action based on data from CrowdSec tools like `get_cti_smoke` or `get_decisions`.

Create a dedicated agent just for monitoring the `get_decisions_stream`. When it detects a new decision, it can use the SDK's handoff feature to pass the details to another, more specialized agent for remediation. This keeps your agent logic clean.

Yes, Vinkius hosts and manages this MCP Server for you. You get a single endpoint token and don't have to worry about hosting, scaling, or maintenance.

The server only processes IP addresses that your agent sends to the tools. Vinkius uses ephemeral, sandboxed environments for each request and never logs or stores the IP addresses you query. All auth is handled by a single token, keeping your credentials separate.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript